generator

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool for administrative tasks like generating random strings for workspace naming and creating directory structures. These operations are part of the intended setup logic and do not involve executing untrusted code or commands.\n- [PROMPT_INJECTION]: As the skill ingests and processes external requirements documents, it has an inherent surface for indirect prompt injection. Ingestion occurs at the prd-loader stage, where user-supplied content is passed to sub-agents. While the orchestrator does not implement explicit sanitization, the risk is mitigated by the modular design and the requirement for user confirmation at multiple checkpoints before the final specification is produced.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:26 AM